Data + AI Engineer

Data + AI Engineer

Job Type: Full-Time / Permanent

Work Location: 100% Remote

Shift Timing: 3 pm – 11 pm IST

Job Summary

Data engineering

• Design and develop scalable data pipelines using Databricks, Spark, SQL and cloud-native
• technologies
• Build and maintain bronze, silver and gold data products following medallion architecture principles
• Develop robust ELT/ETL frameworks supporting batch and streaming workloads
• Implement data modeling standards, optimization strategies and performance tuning practices
• Ensure engineering solutions meet enterprise standards for scalability, reliability and maintainabilityAgentic AI engineering
• Use Speckit and enterprise knowledge repositories to give AI agents contextual grounding, so
• generated code, documentation, tests and engineering artifacts align with organizational standards and
• best practices
• Design knowledge-driven agent workflows that draw on documented business rules, data models, architecture patterns and engineering guidelines
• Build AI-assisted solutions for: Spark and SQL code generation, Data pipeline generation
• Data quality rule generation, Unit test generation, Code review and optimization, CI/CD and deployment automation
• Develop multi-agent workflows that orchestrate end-to-end engineering tasks
• Integrate Large Language Models (LLMs) into enterprise data engineering processes
• Script against REST APIs and SDKs (Power BI/Fabric, Databricks, Jira or Azure DevOps), and use
• Tabular Editor for bulk model changes
• Build evaluation harnesses for AI agents and orchestrate workloads with tools such as Databricks Jobs or Airflow
• Create reusable prompt frameworks, agent instructions, templates and engineering accelerators
• Define guardrails and quality controls for AI-generated code and artifacts
• Implement human-in-the-loop review and governance mechanisms